Unsupervised equalization of lombard effect for speech recognition in noisy adverse environments

IEEE Transactions on Audio, Speech and Language Processing

Volumn 18, Issue 6, 2010, Pages 1379-1393

  Bořil, Hynek ^a   Hansen, John H L ^a  

^a UNIVERSITY OF TEXAS AT DALLAS   (United States)

Author keywords

Cepstral compensation; Codebook of noisy models; Frequency warping; Lombard effect; Speech recognition

Indexed keywords

ACOUSTIC MODEL; ADVERSE ENVIRONMENT; AUTOMATIC SPEECH RECOGNITION SYSTEM; CEPSTRAL; CEPSTRAL DOMAIN; CODEBOOKS; COMPENSATION SCHEME; DECODING STRATEGY; ENVIRONMENTAL NOISE; FREQUENCY DOMAINS; FREQUENCY WARPING; LOMBARD EFFECT; MEAN AND VARIANCE NORMALIZATIONS; PERCEPTUAL LINEAR PREDICTIONS; SPEECH PRODUCTION; SPEECH SPECTRA; UNSUPERVISED EQUALIZATION; WORD ERROR RATE;

ALGORITHMS; FREQUENCY DOMAIN ANALYSIS; MAXIMUM LIKELIHOOD; SIGNAL TO NOISE RATIO; SPEECH COMMUNICATION; WEAVING;

SPEECH RECOGNITION;

EID: 77955734646     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2009.2034770     Document Type: Article

References (66)

1. H. Bořil and J. H. L. Hansen, "Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment," in Proc. ICASSP'09, Taipei, Taiwan, Apr. 2009, pp. 3937-3940.
2. E. Lombard, "Le signe de l'elevation de la voix," Ann. Malad. Oreille, Larynx, Nez, Pharynx, vol.37, pp. 101-119, 1911.
3. J. H. L. Hansen, "Analysis and compensation of stressed and noisy speech with application to robust automatic recognition," Ph.D. dissertation, Georgia Inst. of Technol., Atlanta, GA, 1988.
4. J.-C. Junqua, "The Lombard reflex and its role on human listeners and automatic speech recognizers," J. Acoust. Soc. Amer., vol.93, no.1, pp. 510-524, 1993.
5. J. H. L. Hansen, "Analysis and compensation of speech under stress and noise for environmental robustness in speech recognition," Speech Comm., vol.20, no.1-2, pp. 151-173, 1996.
6. H. Bořil, "Robust speech recogniton: Analysis and equalization of Lombard effect in Czech corpora" Ph.D. dissertation, Czech Technical Univ., Prague, Czech Republic, 2008 [Online]. Available: http://www.utdallas.edu/~hxb076000
7. Y. Lu and M. Cooke, "Speech production modifications produced by competing talkers, babble, and stationary noise," J. Acoust. Soc. Amer., vol.124, no.5, pp. 3261-3275, Nov. 2008.
8. J. J. Dreher and J. O'Neill, "Effects of ambient noise on speaker intelligibility for words and phrases," J. Acoust. Soc. Amer., vol.29, no.12, pp. 1320-1323, 1957.
9. J. C.Webster and R. G. Klumpp, "Effects of ambient noise and nearby talkers on a face-to-face communication task," J. Acoust. Soc. Amer., vol.34, no.7, pp. 936-941, 1962.
10. H. Lane and B. Tranel, "The Lombard sign and the role of hearing in speech," J. Speech Hear. Res., vol.14, pp. 677-709, 1971.
11. H. L. Pick, G. M. Siegel, P. W. Fox, S. R. Garber, and J. K. Kearney, "Inhibiting the Lombard effect," J. Acoust. Soc. Amer., vol.85, no.2, pp. 894-900, 1989.
12. J.-C. Junqua, S. Fincke, and K. Field, "Influence of the speaking style and the noise spectral tilt on the Lombard reflex and automatic speech recognition," in Proc. ICSLP'98, Sydney, Australia, 1998, pp. 467-470.
13. J.-C. Junqua, Sources of Variability and Distortion in the Communication Process. Robust Speech Recognition in Embedded Systems and PC Applications. Dordrecht, The Netherlands: Springer, 2002, pp. 1-36.
14. S. E. Bou-Ghazale and J. H. L. Hansen, "A comparative study of traditional and newly proposed features for recognition of speech under stress," IEEE Trans. Speech Audio Process., vol.8, no.4, pp. 429-442, Jul. 2000.
15. H. Bořil, P. Fousek, and P. Pollák, "Data-driven design of front-end filter bank for Lombard speech recognition," in Proc. ICSLP'06, Pittsburgh, PA, 2006, pp. 381-384.
16. R. Schulman, "Dynamic and perceptual constraints of loud speech," J. Acoust. Soc. Amer., vol. 78, no. S1, pp. S37-S37, 1985.
17. P. Gramming, S. Sundberg, S. Ternström, and W. Perkins, "Relationship between changes in voice pitch and loudness," STL-QPSR, vol.28, no.1, pp. 39-55, 1987.
18. K. Cummings and M. Clements, "Analysis of glottal waveforms across stress styles," in Proc. ICASSP'90, Albuquerque, NM, 1990, vol.1, pp. 369-372.
19. D. Pisoni, R. Bernacki, H. Nusbaum, and M. Yuchtman, "Some acoustic-phonetic correlates of speech produced in noise," in Proc. ICASSP'85, Tampa, FL, 1985, vol.10, pp. 1581-1584.
20. W. V. Summers, D. B. Pisoni, R. H. Bernacki, R. I. Pedlow, and M. A. Stokes, "Effects of noise on speech production: Acoustic and perceptual analyses," J. Acoust. Soc. Amer., vol.84, no.3, pp. 917-928, 1988.
21. R. D. Kent and C. Read, The Acoustic Analysis of Speech. San Diego, CA: Whurr, 1992.
22. Z. Bond and T. Moore, "A note on loud and Lombard speech," in Proc. ICSLP'90, Kobe, Japan, 1990, pp. 969-972.
23. J. Junqua and Y. Anglade, "Acoustic and perceptual studies of Lombard speech: Application to isolated-words automatic speech recognition," in Proc. ICASSP'90, Albuquerque, NM, 1990, vol.2, pp. 841-844.
24. Z. S. Bond, T. J. Moore, and B. Gable, "Acoustic-Phonetic characteristics of speech produced in noise and while wearing an oxygen mask," J. Acoust. Soc. Amer., vol.85, no.2, pp. 907-912, 1989.
25. J. Hansen and O. Bria, "Lombard effect compensation for robust automatic speech recognition in noise," in Proc. ICSLP'90, Kobe, Japan, 1990, pp. 1125-1128.
26. S. B. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," IEEE Trans. Acoust., Speech, Signal Process., vol.ASSP-28, no.4, pp. 357-366, Aug. 1980.
27. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. Amer., vol.87, no.4, pp. 1738-1752, 1990.
28. R. P. Lippmann, E. A. Martin, and D. B. Paul, "Multi-style training for robust isolated-word speech recognition," in Proc. ICASSP'87, Dallas, TX, 1987, pp. 705-708.
29. R. W. Schafer and L. R. Rabiner, "System for automatic formant analysis of voiced speech," J. Acoust. Soc. Amer., vol. 47, no. 2B, pp. 634-648, 1970.
30. U. H. Yapanel and J. H. L. Hansen, "A new perceptually motivated MVDR-based acoustic front-end (PMVDR) for robust automatic speech recognition," Speech Commun., vol.50, no.2, pp. 142-152, 2008.
31. B. A. Hanson and T. H. Applebaum, "Features for noise-robust speaker-independent word recognition," in Proc. ICSLP'90, Kobe, Japan, 1990, pp. 1117-1120.
32. J. H. L. Hansen and M. A. Clements, "Constrained iterative speech enhancement with application to speech recognition," IEEE Trans. Signal Process., vol.39, no.4, pp. 795-805, Apr. 1991.
33. Y. Takizawa and M. Hamada, "Lombard speech recognition by formant-frequency-shifted LPC cepstrum," in Proc. ICSLP'90, Kobe, Japan, 1990, pp. 293-296.
34. T. Suzuki, K. Nakajima, and Y. Abe, "Isolated word recognition using models for acoustic phonetic variability by Lombard effect," in Proc. ICSLP'94, Yokohama, Japan, 1994, pp. 999-1002.
35. D. B. Paul, "A speaker-stress resistantHMMisolatedword recognizer," in Proc. ICASSP'87, Dallas, TX, 1987, pp. 713-716.
36. B. D. Womack and J. Hansen, "N-channel hidden Markov models for combined stress speech classification and recognition," IEEE Trans. Speech Audio Process., vol.7, no.6, pp. 668-677, 1999.
37. B. D. Womack and J. Hansen, "Classification of speech under stress using target driven features," Speech Commun., Special Iss. Speech Under Stress, vol.20, no.1-2, pp. 131-150, 1996.
38. H. Bořil, P. Fousek, and H. Höge, "Two-stage system for robust neutral/ Lombard speech recognition," in Proc. Interspeech'07, Antwerp, Belgium, 2007, pp. 1074-1077.
39. B. Womack and J. Hansen, "Stress independent robust HMM speech recognition using neural network stress classification," in Proc. Eurospeech' 95, Madrid, Spain, 1995, pp. 1999-2002.
40. S. E. Bou-Ghazale and J. Hansen, "HMM-based stressed speech modeling with application to improved synthesis and recognition of isolated speech under stress," IEEE Trans. Speech Audio Process., vol.6, no.3, pp. 201-216, 1998.
41. J. Hansen and V.Varadarajan, "Analysis and compensation of Lombard speech across noise type and levels with application to in-set/out-of-set speaker recognition," IEEE Trans. Audio, Speech, Lang. Process., vol.17, no.2, pp. 366-378, Feb. 2009.
42. L. Lee and R. Rose, "Speaker normalization using efficient frequency warping procedures," in Proc. ICASSP'96, Los Alamitos, CA, 1996, vol.1, pp. 353-356, IEEE Comput. Soc..
43. S. Dharanipragada and M. Padmanabha, "A nonlinear unsupervised adaptation technique for speech recognition," in Proc. ICSLP-2000, 2000, vol.4, pp. 556-559.
44. F. Hilger and H. Ney, "Quantile based histogram equalization for noise robust large vocabulary speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol.14, no.3, pp. 845-854, May 2006.
45. B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol.55, no.6, pp. 1304-1312, 1974.
46. O. Viikki and K. Laurila, "Noise robust HMM-based speech recognition using segmental cepstral feature vector normal," in ESCA-NATO Workshop RSR, 1997, vol.1, pp. 107-110.
47. S. Yoshizawa, N. Hayasaka, N. Wada, and Y. Miyanaga, "Cepstral gain normalization for noise robust speech recognition," in Proc. ICASSP'04, May 2004, vol.1, pp. I-209-I-212.
48. H. Wakita, "Normalization of vowels by vocal-tract length and its application to vowel identification," IEEE Trans. Acoust., Speech, Signal Process., vol.25, no.2, pp. 183-192, Apr. 1977.
49. E. Eide and H. Gish, "A parametric approach to vocal tract length normalization," in Proc. ICASSP'96, Los Alamitos, CA, 1996, vol.1, pp. 346-348, IEEE Comput. Soc..
50. P. Zhan and M. Westphal, "Speaker normalization based on frequency warping," in Proc. ICASSP'97, 1997, vol.2, pp. 1039-1042.
51. M. Pitz and H. Ney, "Vocal tract normalization equals linear transformation in cepstral space," IEEE Trans. Audio, Speech, Lang. Process., vol.13, no.5, pp. 930-944, Sep. 2005.
52. J. P. Openshaw and J. S. Mason, "Optimal noise-masking of cepstral features for robust speaker identification," in Proc. ESCAWorkshop Automatic Speaker Recog., Identification, and Verification-ASRIV-1994, 1994, vol.1, pp. 231-234.
53. F. de Wet, J. de Veth, L. Boves, and B. Cranen, "Additive background noise as a source of non-linear mismatch in the cepstral and log-energy domain," Comput. Speech Lang., vol.19, no.1, pp. 31-54, Jan. 2005.
54. S. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust., Speech, Signal Process., vol.27, no.2, pp. 113-120, 1979. (Pubitemid 9467471)
55. J. A. Rice,Mathematical Statistics and Data Analysis. Belmont, CA: Duxbury, 1995.
56. L. Rabiner and R. Schafer, Digital Processing of Speech Signals. Englewood Cliffs, NJ: Prentice-Hall, 1978.
57. K. Yao, K. K. Paliwal, and S. Nakamura, "Noise adaptive speech recognition based on sequential noise parameter estimation," Speech Commun., vol.42, no.1, pp. 5-23, 2004.
58. C. E. Mokbel and G. Chollet, "Automatic word recognition in cars," IEEE Trans. Speech Audio Process., vol.3, no.5, pp. 346-356, Sep. 1995.
59. A. P. Varga and R. K. Moore, "Hidden Markov model decomposition of speech and noise," in Proc. ICASSP'90, Albuquerque, NM, 1990, vol.21, pp. 845-848.
60. M. Gales and S. Young, "Robust continuous speech recognition using parallel model combination," IEEE Trans. Speech Audio Process., vol.4, no.5, pp. 352-359, Sep. 1996.
61. P. Pollák, J. Vopička, and P. Sovka, "Czech language database of car speech and environmental noise," in Proc. Eurospeech'99, Budapest, Hungary, 1999, pp. 2263-2266.
62. H. Bořil, T. Bořil, and P. Pollák, "Methodology of Lombard speech database acquisition: Experiences with CLSD," in Proc. LREC 2006-5th Conf. Lang. Res. Eval., Genova, Italy, 2006, pp. 1644-1647.
63. D. Iskra, B. Grosskopf, K. Marasek, H. van den Huevel, F. Diehl, and A. Kiessling, "Speecon-Speech databases for consumer devices: Database specification and validation," in Proc. LREC'2002, Las Palmas, Spain, 2002.
64. L. Welling, H. Ney, and S. Kanthak, "Speaker adaptive modeling by vocal tract normalization," IEEE Trans. Speech Audio Process., vol.10, no.6, pp. 415-426, Sep. 2002.
65. J. H. L. Hansen and M. Clements, "Stress compensation and noise reduction algorithms for robust speech recognition," in Proc. ICASSP'89, Glasgow, U.K., 1989, pp. 266-269.
66. J. Pelecanos and S. Sridharan, "Feature warping for robust speaker verification," in Proc. ODYSSEY-2001, Crete, Greece, 2001, pp. 213-218.